tim-lawson
commited on
Commit
•
42e8272
1
Parent(s):
ae7964d
Push model using huggingface_hub.
Browse files- README.md +6 -2
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -6,16 +6,20 @@ tags:
|
|
6 |
- arxiv:2409.04185
|
7 |
- model_hub_mixin
|
8 |
- pytorch_model_hub_mixin
|
9 |
-
base_model: EleutherAI/pythia-70m-deduped
|
10 |
---
|
11 |
|
12 |
-
# Model Card for
|
13 |
|
14 |
A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream activation
|
15 |
vectors from [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) with an
|
16 |
expansion factor of R = 64 and sparsity k = 32, over 1 billion
|
17 |
tokens from [monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).
|
18 |
|
|
|
|
|
|
|
|
|
|
|
19 |
### Model Sources
|
20 |
|
21 |
- **Repository:** <https://github.com/tim-lawson/mlsae>
|
|
|
6 |
- arxiv:2409.04185
|
7 |
- model_hub_mixin
|
8 |
- pytorch_model_hub_mixin
|
|
|
9 |
---
|
10 |
|
11 |
+
# Model Card for tim-lawson/sae-pythia-70m-deduped-x64-k32-tfm-layers-5
|
12 |
|
13 |
A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream activation
|
14 |
vectors from [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) with an
|
15 |
expansion factor of R = 64 and sparsity k = 32, over 1 billion
|
16 |
tokens from [monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).
|
17 |
|
18 |
+
|
19 |
+
This model is a PyTorch Lightning MLSAETransformer module, which includes the underlying
|
20 |
+
transformer.
|
21 |
+
|
22 |
+
|
23 |
### Model Sources
|
24 |
|
25 |
- **Repository:** <https://github.com/tim-lawson/mlsae>
|
config.json
CHANGED
@@ -15,6 +15,6 @@
|
|
15 |
"max_length": 2048,
|
16 |
"model_name": "EleutherAI/pythia-70m-deduped",
|
17 |
"skip_special_tokens": true,
|
18 |
-
"standardize":
|
19 |
"tuned_lens": false
|
20 |
}
|
|
|
15 |
"max_length": 2048,
|
16 |
"model_name": "EleutherAI/pythia-70m-deduped",
|
17 |
"skip_special_tokens": true,
|
18 |
+
"standardize": false,
|
19 |
"tuned_lens": false
|
20 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 415936592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffd0dd60112fe375059f0be3ef1ff2bc238c686fa6e8a0e278c5fae4aa0b3a25
|
3 |
size 415936592
|